Training checkpoint - Epoch 1, Step 8988

checkpoint-8988/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

checkpoint-8988/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-8988/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.53.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-8988/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178e6730d4cc0f4badea61184ceb100311dae5a03d9fc1c8a339d048069347ea
+size 90864192

checkpoint-8988/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

checkpoint-8988/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac540ef5cb7ff1d2b637b8e3606fe1071047616f26be92584061daed3a65d72c
+size 180607738

checkpoint-8988/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a54d006cc1b47e69fdf8fb03e26500e8d33488b63240411da0349b4a34221c
+size 14244

checkpoint-8988/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b286a7e7a9a858200bb5f12e36ced120de41de00ce620c2476c243e8108718
+size 988

checkpoint-8988/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2514e3acc1710081499832450c5372969171dac97d3962b6b822b59cd8e5f3c8
+size 1064

checkpoint-8988/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

checkpoint-8988/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-8988/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

checkpoint-8988/trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2000,
+  "global_step": 8988,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00011125945705384957,
+      "grad_norm": 6.3739542961120605,
+      "learning_rate": 0.0,
+      "loss": 2.9555,
+      "step": 1
+    },
+    {
+      "epoch": 0.22251891410769917,
+      "grad_norm": 4.010181903839111,
+      "learning_rate": 6.672972070768888e-06,
+      "loss": 2.5193,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22251891410769917,
+      "eval_cosine_accuracy": 0.9481027126312256,
+      "eval_loss": 1.1309852600097656,
+      "eval_runtime": 23.41,
+      "eval_samples_per_second": 404.144,
+      "eval_steps_per_second": 1.581,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44503782821539833,
+      "grad_norm": 4.1902337074279785,
+      "learning_rate": 1.3349282296650718e-05,
+      "loss": 1.9678,
+      "step": 4000
+    },
+    {
+      "epoch": 0.44503782821539833,
+      "eval_cosine_accuracy": 0.949688196182251,
+      "eval_loss": 1.11049485206604,
+      "eval_runtime": 24.2815,
+      "eval_samples_per_second": 389.638,
+      "eval_steps_per_second": 1.524,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "grad_norm": 4.1325764656066895,
+      "learning_rate": 2.002559252253255e-05,
+      "loss": 1.6578,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "eval_cosine_accuracy": 0.9524363279342651,
+      "eval_loss": 1.1041761636734009,
+      "eval_runtime": 23.4441,
+      "eval_samples_per_second": 403.556,
+      "eval_steps_per_second": 1.578,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8900756564307967,
+      "grad_norm": 3.8412773609161377,
+      "learning_rate": 2.6691888283075553e-05,
+      "loss": 1.4707,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8900756564307967,
+      "eval_cosine_accuracy": 0.9552901387214661,
+      "eval_loss": 1.0991708040237427,
+      "eval_runtime": 27.9755,
+      "eval_samples_per_second": 338.189,
+      "eval_steps_per_second": 1.323,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 26964,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8988/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c8cb1d24d97906396a3e8a8563e441cbd928845495cfe113d5d72fbf9fa65c
+size 5624

checkpoint-8988/training_metrics.json

@@ -0,0 +1,30 @@
+{
+  "metrics_history": [
+    {
+      "epoch": 0.22251891410769917,
+      "global_step": 2000,
+      "eval_loss": 1.1309852600097656,
+      "eval_cosine_accuracy": 0.9481027126312256
+    },
+    {
+      "epoch": 0.44503782821539833,
+      "global_step": 4000,
+      "eval_loss": 1.11049485206604,
+      "eval_cosine_accuracy": 0.949688196182251
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "global_step": 6000,
+      "eval_loss": 1.1041761636734009,
+      "eval_cosine_accuracy": 0.9524363279342651
+    },
+    {
+      "epoch": 0.8900756564307967,
+      "global_step": 8000,
+      "eval_loss": 1.0991708040237427,
+      "eval_cosine_accuracy": 0.9552901387214661
+    }
+  ],
+  "current_epoch": 1,
+  "global_step": 8988
+}